Episode

#526: Building Data Science with Foundation LLM Models

Podcast
Talk Python To Me
Published
Nov 1, 2025
Duration seconds
4044
Processing state
processed
Canonical source
https://talkpython.fm/episodes/show/526/building-data-science-with-foundation-llm-models
Audio
https://talkpython.fm/episodes/download/526/building-data-science-with-foundation-llm-models.mp3?v=2
JSON
/v1/public/podcasts/talk-python-to-me/episodes/526-building-data-science-with-foundation-llm-models
Markdown
/podcast/talk-python-to-me/526-building-data-science-with-foundation-llm-models.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/talk-python-to-me/episodes/526-building-data-science-with-foundation-llm-models/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/talk-python-to-me/526-building-data-science-with-foundation-llm-models.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

Today, we’re talking about building real AI products with foundation models. Not toy demos, not vibes. We’ll get into the boring dashboards that save launches, evals that change your mind, and the shift from analyst to AI app builder. Our guide is Hugo Bowne-Anderson, educator, podcaster, and data scientist, who’s been in the trenches from scalable Python to LLM apps. If you care about shipping LLM features without burning the house down, stick around.